summaryrefslogtreecommitdiff
path: root/Build/source/libs/icu/icu-50.1/tools/gensprep/gensprep.c
blob: 94ba08d89b9394637584e360bdb0260d76c00e1e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
/*
*******************************************************************************
*
*   Copyright (C) 2003-2012, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  gensprep.c
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2003-02-06
*   created by: Ram Viswanadha
*
*   This program reads the Profile.txt files,
*   parses them, and extracts the data for StringPrep profile.
*   It then preprocesses it and writes a binary file for efficient use
*   in various StringPrep conversion processes.
*/

#define USPREP_TYPE_NAMES_ARRAY 1

#include <stdio.h>
#include <stdlib.h>

#include "cmemory.h"
#include "cstring.h"
#include "unewdata.h"
#include "uoptions.h"
#include "uparse.h"
#include "sprpimpl.h"

#include "unicode/uclean.h"
#include "unicode/udata.h"
#include "unicode/utypes.h"
#include "unicode/putil.h"


U_CDECL_BEGIN
#include "gensprep.h"
U_CDECL_END

UBool beVerbose=FALSE, haveCopyright=TRUE;

#define NORM_CORRECTIONS_FILE_NAME "NormalizationCorrections.txt"

#define NORMALIZE_DIRECTIVE "normalize"
#define NORMALIZE_DIRECTIVE_LEN 9
#define CHECK_BIDI_DIRECTIVE "check-bidi"
#define CHECK_BIDI_DIRECTIVE_LEN 10

/* prototypes --------------------------------------------------------------- */

static void
parseMappings(const char *filename, UBool reportError, UErrorCode *pErrorCode);

static void
parseNormalizationCorrections(const char *filename, UErrorCode *pErrorCode);


/* -------------------------------------------------------------------------- */

static UOption options[]={
    UOPTION_HELP_H,
    UOPTION_HELP_QUESTION_MARK,
    UOPTION_VERBOSE,
    UOPTION_COPYRIGHT,
    UOPTION_DESTDIR,
    UOPTION_SOURCEDIR,
    UOPTION_ICUDATADIR,
    UOPTION_BUNDLE_NAME,
    { "normalization", NULL, NULL, NULL, 'n', UOPT_REQUIRES_ARG, 0 },
    { "norm-correction", NULL, NULL, NULL, 'm', UOPT_REQUIRES_ARG, 0 },
    { "check-bidi", NULL, NULL, NULL,  'k', UOPT_NO_ARG, 0},
    { "unicode", NULL, NULL, NULL, 'u', UOPT_REQUIRES_ARG, 0 },
};

enum{
    HELP,
    HELP_QUESTION_MARK,
    VERBOSE,
    COPYRIGHT,
    DESTDIR,
    SOURCEDIR,
    ICUDATADIR,
    BUNDLE_NAME,
    NORMALIZE,
    NORM_CORRECTION_DIR,
    CHECK_BIDI,
    UNICODE_VERSION
};

static int printHelp(int argc, char* argv[]){
    /*
     * Broken into chucks because the C89 standard says the minimum
     * required supported string length is 509 bytes.
     */
    fprintf(stderr,
        "Usage: %s [-options] [file_name]\n"
        "\n"
        "Read the files specified and\n"
        "create a binary file [package-name]_[bundle-name]." DATA_TYPE " with the StringPrep profile data\n"
        "\n",
        argv[0]);
    fprintf(stderr,
        "Options:\n"
        "\t-h or -? or --help       print this usage text\n"
        "\t-v or --verbose          verbose output\n"
        "\t-c or --copyright        include a copyright notice\n");
    fprintf(stderr,
        "\t-d or --destdir          destination directory, followed by the path\n"
        "\t-s or --sourcedir        source directory of ICU data, followed by the path\n"
        "\t-b or --bundle-name      generate the ouput data file with the name specified\n"
        "\t-i or --icudatadir       directory for locating any needed intermediate data files,\n"
        "\t                         followed by path, defaults to %s\n",
        u_getDataDirectory());
    fprintf(stderr,
        "\t-n or --normalize        turn on the option for normalization and include mappings\n"
        "\t                         from NormalizationCorrections.txt from the given path,\n"
        "\t                         e.g: /test/icu/source/data/unidata\n");
    fprintf(stderr,
        "\t-m or --norm-correction  use NormalizationCorrections.txt from the given path\n"
        "\t                         when the input file contains a normalization directive.\n"
        "\t                         unlike -n/--normalize, this option does not force the\n"
        "\t                         normalization.\n");
    fprintf(stderr,
        "\t-k or --check-bidi       turn on the option for checking for BiDi in the profile\n"
        "\t-u or --unicode          version of Unicode to be used with this profile followed by the version\n"
        );
    return argc<0 ? U_ILLEGAL_ARGUMENT_ERROR : U_ZERO_ERROR;
}


extern int
main(int argc, char* argv[]) {
#if !UCONFIG_NO_IDNA
    char* filename = NULL;
#endif
    const char *srcDir=NULL, *destDir=NULL, *icuUniDataDir=NULL;
    const char *bundleName=NULL, *inputFileName = NULL;
    char *basename=NULL;
    int32_t sprepOptions = 0;

    UErrorCode errorCode=U_ZERO_ERROR;

    U_MAIN_INIT_ARGS(argc, argv);

    /* preset then read command line options */
    options[DESTDIR].value=u_getDataDirectory();
    options[SOURCEDIR].value="";
    options[UNICODE_VERSION].value="0"; /* don't assume the unicode version */
    options[BUNDLE_NAME].value = DATA_NAME;
    options[NORMALIZE].value = "";

    argc=u_parseArgs(argc, argv, sizeof(options)/sizeof(options[0]), options);

    /* error handling, printing usage message */
    if(argc<0) {
        fprintf(stderr,
            "error in command line argument \"%s\"\n",
            argv[-argc]);
    }
    if(argc<0 || options[HELP].doesOccur || options[HELP_QUESTION_MARK].doesOccur) {
        return printHelp(argc, argv);
        
    }

    /* get the options values */
    beVerbose=options[VERBOSE].doesOccur;
    haveCopyright=options[COPYRIGHT].doesOccur;
    srcDir=options[SOURCEDIR].value;
    destDir=options[DESTDIR].value;
    bundleName = options[BUNDLE_NAME].value;
    if(options[NORMALIZE].doesOccur) {
        icuUniDataDir = options[NORMALIZE].value;
    } else {
        icuUniDataDir = options[NORM_CORRECTION_DIR].value;
    }

    if(argc<2) {
        /* print the help message */
        return printHelp(argc, argv);
    } else {
        inputFileName = argv[1];
    }
    if(!options[UNICODE_VERSION].doesOccur){
        return printHelp(argc, argv);
    }
    if(options[ICUDATADIR].doesOccur) {
        u_setDataDirectory(options[ICUDATADIR].value);
    }
#if UCONFIG_NO_IDNA

    fprintf(stderr,
        "gensprep writes dummy " U_ICUDATA_NAME "_" DATA_NAME "." DATA_TYPE
        " because UCONFIG_NO_IDNA is set, \n"
        "see icu/source/common/unicode/uconfig.h\n");
    generateData(destDir, bundleName);

#else

    setUnicodeVersion(options[UNICODE_VERSION].value);
    filename = (char* ) uprv_malloc(uprv_strlen(srcDir) + 300); /* hopefully this should be enough */
   
    /* prepare the filename beginning with the source dir */
    if(uprv_strchr(srcDir,U_FILE_SEP_CHAR) == NULL && uprv_strchr(srcDir,U_FILE_ALT_SEP_CHAR) == NULL){
        filename[0] = '.';
        filename[1] = U_FILE_SEP_CHAR;
        uprv_strcpy(filename+2,srcDir);
    }else{
        uprv_strcpy(filename, srcDir);
    }
    
    basename=filename+uprv_strlen(filename);
    if(basename>filename && *(basename-1)!=U_FILE_SEP_CHAR) {
        *basename++=U_FILE_SEP_CHAR;
    }
    
    /* initialize */
    init();

    /* process the file */
    uprv_strcpy(basename,inputFileName);
    parseMappings(filename,FALSE, &errorCode);
    if(U_FAILURE(errorCode)) {
        fprintf(stderr, "Could not open file %s for reading. Error: %s \n", filename, u_errorName(errorCode));
        return errorCode;
    }
    
    if(options[NORMALIZE].doesOccur){ /* this option might be set by @normalize;; in the source file */
        /* set up directory for NormalizationCorrections.txt */
        uprv_strcpy(filename,icuUniDataDir);
        basename=filename+uprv_strlen(filename);
        if(basename>filename && *(basename-1)!=U_FILE_SEP_CHAR) {
            *basename++=U_FILE_SEP_CHAR;
        }

        *basename++=U_FILE_SEP_CHAR;
        uprv_strcpy(basename,NORM_CORRECTIONS_FILE_NAME);
    
        parseNormalizationCorrections(filename,&errorCode);
        if(U_FAILURE(errorCode)){
            fprintf(stderr,"Could not open file %s for reading \n", filename);
            return errorCode;
        }
        sprepOptions |= _SPREP_NORMALIZATION_ON;
    }
    
    if(options[CHECK_BIDI].doesOccur){ /* this option might be set by @check-bidi;; in the source file */
        sprepOptions |= _SPREP_CHECK_BIDI_ON;
    }

    setOptions(sprepOptions);

    /* process parsed data */
    if(U_SUCCESS(errorCode)) {
        /* write the data file */
        generateData(destDir, bundleName);

        cleanUpData();
    }

    uprv_free(filename);

    u_cleanup();

#endif

    return errorCode;
}

#if !UCONFIG_NO_IDNA

static void U_CALLCONV
normalizationCorrectionsLineFn(void *context,
                    char *fields[][2], int32_t fieldCount,
                    UErrorCode *pErrorCode) {
    uint32_t mapping[40];
    char *end, *s;
    uint32_t code;
    int32_t length;
    UVersionInfo version;
    UVersionInfo thisVersion;

    /* get the character code, field 0 */
    code=(uint32_t)uprv_strtoul(fields[0][0], &end, 16);
    if(U_FAILURE(*pErrorCode)) {
        fprintf(stderr, "gensprep: error parsing NormalizationCorrections.txt mapping at %s\n", fields[0][0]);
        exit(*pErrorCode);
    }
    /* Original (erroneous) decomposition */
    s = fields[1][0];

    /* parse the mapping string */
    length=u_parseCodePoints(s, mapping, sizeof(mapping)/4, pErrorCode);

    /* ignore corrected decomposition */

    u_versionFromString(version,fields[3][0] );
    u_versionFromString(thisVersion, "3.2.0");



    if(U_FAILURE(*pErrorCode)) {
        fprintf(stderr, "gensprep error parsing NormalizationCorrections.txt of U+%04lx - %s\n",
                (long)code, u_errorName(*pErrorCode));
        exit(*pErrorCode);
    }

    /* store the mapping */
    if( version[0] > thisVersion[0] || 
        ((version[0]==thisVersion[0]) && (version[1] > thisVersion[1]))
        ){
        storeMapping(code,mapping, length, USPREP_MAP, pErrorCode);
    }
    setUnicodeVersionNC(version);
}

static void
parseNormalizationCorrections(const char *filename, UErrorCode *pErrorCode) {
    char *fields[4][2];

    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return;
    }

    u_parseDelimitedFile(filename, ';', fields, 4, normalizationCorrectionsLineFn, NULL, pErrorCode);

    /* fprintf(stdout,"Number of code points that have NormalizationCorrections mapping with length >1 : %i\n",len); */

    if(U_FAILURE(*pErrorCode) && ( *pErrorCode!=U_FILE_ACCESS_ERROR)) {
        fprintf(stderr, "gensprep error: u_parseDelimitedFile(\"%s\") failed - %s\n", filename, u_errorName(*pErrorCode));
        exit(*pErrorCode);
    }
}

static void U_CALLCONV
strprepProfileLineFn(void *context,
              char *fields[][2], int32_t fieldCount,
              UErrorCode *pErrorCode) {
    uint32_t mapping[40];
    char *end, *map;
    uint32_t code;
    int32_t length;
   /*UBool* mapWithNorm = (UBool*) context;*/
    const char* typeName;
    uint32_t rangeStart=0,rangeEnd =0;
    const char* filename = (const char*) context;
    const char *s;

    s = u_skipWhitespace(fields[0][0]);
    if (*s == '@') {
        /* special directive */
        s++;
        length = fields[0][1] - s;
        if (length >= NORMALIZE_DIRECTIVE_LEN
            && uprv_strncmp(s, NORMALIZE_DIRECTIVE, NORMALIZE_DIRECTIVE_LEN) == 0) {
            options[NORMALIZE].doesOccur = TRUE;
            return;
        }
        else if (length >= CHECK_BIDI_DIRECTIVE_LEN
            && uprv_strncmp(s, CHECK_BIDI_DIRECTIVE, CHECK_BIDI_DIRECTIVE_LEN) == 0) {
            options[CHECK_BIDI].doesOccur = TRUE;
            return;
        }
        else {
            fprintf(stderr, "gensprep error parsing a directive %s.", fields[0][0]);
        }
    }

    typeName = fields[2][0];
    map = fields[1][0];

    if(uprv_strstr(typeName, usprepTypeNames[USPREP_UNASSIGNED])!=NULL){

        u_parseCodePointRange(s, &rangeStart,&rangeEnd, pErrorCode);
        if(U_FAILURE(*pErrorCode)){
            fprintf(stderr, "Could not parse code point range. Error: %s\n",u_errorName(*pErrorCode));
            return;
        }

        /* store the range */
        storeRange(rangeStart,rangeEnd,USPREP_UNASSIGNED, pErrorCode);

    }else if(uprv_strstr(typeName, usprepTypeNames[USPREP_PROHIBITED])!=NULL){

        u_parseCodePointRange(s, &rangeStart,&rangeEnd, pErrorCode);
        if(U_FAILURE(*pErrorCode)){
            fprintf(stderr, "Could not parse code point range. Error: %s\n",u_errorName(*pErrorCode));
            return;
        }

        /* store the range */
        storeRange(rangeStart,rangeEnd,USPREP_PROHIBITED, pErrorCode);

    }else if(uprv_strstr(typeName, usprepTypeNames[USPREP_MAP])!=NULL){

        /* get the character code, field 0 */
        code=(uint32_t)uprv_strtoul(s, &end, 16);
        if(end<=s || end!=fields[0][1]) {
            fprintf(stderr, "gensprep: syntax error in field 0 at %s\n", fields[0][0]);
            *pErrorCode=U_PARSE_ERROR;
            exit(U_PARSE_ERROR);
        }

        /* parse the mapping string */
        length=u_parseCodePoints(map, mapping, sizeof(mapping)/4, pErrorCode);
        
        /* store the mapping */
        storeMapping(code,mapping, length,USPREP_MAP, pErrorCode);

    }else{
        *pErrorCode = U_INVALID_FORMAT_ERROR;
    }
    
    if(U_FAILURE(*pErrorCode)) {
        fprintf(stderr, "gensprep error parsing  %s line %s at %s. Error: %s\n",filename,
               fields[0][0],fields[2][0],u_errorName(*pErrorCode));
        exit(*pErrorCode);
    }

}

static void
parseMappings(const char *filename, UBool reportError, UErrorCode *pErrorCode) {
    char *fields[3][2];

    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return;
    }

    u_parseDelimitedFile(filename, ';', fields, 3, strprepProfileLineFn, (void*)filename, pErrorCode);

    /*fprintf(stdout,"Number of code points that have mappings with length >1 : %i\n",len);*/

    if(U_FAILURE(*pErrorCode) && (reportError || *pErrorCode!=U_FILE_ACCESS_ERROR)) {
        fprintf(stderr, "gensprep error: u_parseDelimitedFile(\"%s\") failed - %s\n", filename, u_errorName(*pErrorCode));
        exit(*pErrorCode);
    }
}


#endif /* #if !UCONFIG_NO_IDNA */

/*
 * Hey, Emacs, please set the following:
 *
 * Local Variables:
 * indent-tabs-mode: nil
 * End:
 *
 */